Batch DropBlock Network for Person Re-identification and Beyond
arXiv:1811.07130
Abstract
Since the person re-identification task often suffers from the problem of pose changes and occlusions, some attentive local features are often suppressed when training CNNs. In this paper, we propose the Batch DropBlock (BDB) Network which is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch. The global branch encodes the global salient representations. Meanwhile, the feature dropping branch consists of an attentive feature learning module called Batch DropBlock, which randomly drops the same region of all input feature maps in a batch to reinforce the attentive feature learning of local regions. The network then concatenates features from both branches and provides a more comprehensive and spatially distributed feature representation. Albeit simple, our method achieves state-of-the-art on person re-identification and it is also applicable to general metric learning tasks. For instance, we achieve 76.4% Rank-1 accuracy on the CUHK03-Detect dataset and 83.0% Recall-1 score on the Stanford Online Products dataset, outperforming the existing works by a large margin (more than 6%).
Accepted by ICCV 2019
References in corpus (22)
- In Defense of the Triplet Loss for Person Re-Identification
- Improved Regularization of Convolutional Neural Networks with Cutout
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Person Re-identification: Past, Present and Future
- Random Erasing Data Augmentation
- Pedestrian Alignment Network for Large-scale Person Re-identification
- DropBlock: A regularization method for convolutional networks
- Deep Representation Learning with Part Loss for Person Re-Identification
- AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
- GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
- Learning Deep Embeddings with Histogram Loss
- Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
- Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
- Harmonious Attention Network for Person Re-Identification
- Pose Invariant Embedding for Deep Person Re-identification
- Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
- Beyond triplet loss: a deep quadruplet network for person re-identification
- Re-ID done right: towards good practices for person re-identification
- HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
- A Siamese Long Short-Term Memory Architecture for Human Re-Identification
- Deep Group-shuffling Random Walk for Person Re-identification
- Pose-Aware Person Recognition
Cited by in corpus (5)
- Bag of Tricks and A Strong Baseline for Deep Person Re-identification
- Second-order Non-local Attention Networks for Person Re-identification
- Cluster Contrast for Unsupervised Person Re-Identification
- Temporal Complementary Learning for Video Person Re-Identification
- A Benchmark on Tricks for Large-scale Image Retrieval